Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 477  50 755 149 509  75 416 421 444 993 644 419  70 754 843 683 826  55 409 344
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 826  NA 477 754  NA 344 421  70 419 509  50 993 644  55 444 149  75 843 409 755 416 683  NA
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 5 4 3 2 4 4 1 5 4 1
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "v" "e" "h" "r" "q" "F" "L" "N" "G" "H"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 10
which( manyNumbersWithNA > 900 )
[1] 12
which( is.na( manyNumbersWithNA ) )
[1]  2  5 23

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 993
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 993
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 993

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "F" "L" "N" "G" "H"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "v" "e" "h" "r" "q"
manyNumbers %in% 300:600
 [1]  TRUE FALSE FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE
which( manyNumbers %in% 300:600 )
[1]  1  5  7  8  9 12 19 20
sum( manyNumbers %in% 300:600 )
[1] 8

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" NA      "small" "large" NA      "small" "small" "small" "small" "large" "small" "large" "large" "small" "small" "small" "small" "large"
[19] "small" "large" "small" "large" NA     
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "UNKNOWN" "small"   "large"   "UNKNOWN" "small"   "small"   "small"   "small"   "large"   "small"   "large"   "large"   "small"  
[15] "small"   "small"   "small"   "large"   "small"   "large"   "small"   "large"   "UNKNOWN"
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1] 826  NA   0 754  NA   0   0   0   0 509   0 993 644   0   0   0   0 843   0 755   0 683  NA

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 5 4 3 2 1
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  5  4  3  2  1
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE FALSE  TRUE  TRUE FALSE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 12
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 993
which.min( manyNumbersWithNA )
[1] 11
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 50
range( manyNumbersWithNA, na.rm = TRUE )
[1]  50 993

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 826  NA 477 754  NA 344 421  70 419 509  50 993 644  55 444 149  75 843 409 755 416 683  NA
sort( manyNumbersWithNA )
 [1]  50  55  70  75 149 344 409 416 419 421 444 477 509 644 683 754 755 826 843 993
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  50  55  70  75 149 344 409 416 419 421 444 477 509 644 683 754 755 826 843 993  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 993 843 826 755 754 683 644 509 477 444 421 419 416 409 344 149  75  70  55  50  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 826  NA 477 754  NA
order( manyNumbersWithNA[1:5] )
[1] 3 4 1 2 5
rank( manyNumbersWithNA[1:5] )
[1] 3 4 1 2 5
sort( mixedLetters )
 [1] "e" "F" "G" "h" "H" "L" "N" "q" "r" "v"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 10.0  6.5  6.5  8.5  2.5  8.5  2.5  4.5  1.0  4.5
rank( manyDuplicates, ties.method = "min" )
 [1] 10  6  6  8  2  8  2  4  1  4
rank( manyDuplicates, ties.method = "random" )
 [1] 10  7  6  8  3  9  2  4  1  5

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000  0.2263173  0.9131569  1.0953023  1.5933083  1.2130246 -0.1663922 -2.0174914 -0.8576936
[14]  1.2654270  1.5191323
round( v, 0 )
 [1] -1  0  0  0  1  0  1  1  2  1  0 -2 -1  1  2
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  0.2  0.9  1.1  1.6  1.2 -0.2 -2.0 -0.9  1.3  1.5
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  0.23  0.91  1.10  1.59  1.21 -0.17 -2.02 -0.86  1.27  1.52
floor( v )
 [1] -1 -1  0  0  1  0  0  1  1  1 -1 -3 -1  1  1
ceiling( v )
 [1] -1  0  0  1  1  1  1  2  2  2  0 -2  0  2  2

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC